Two years ago, engineers released DeepBach, a neural network that generates Baroque anthems almost indistinguishable from Bach’s, but still nobody can decide if it’s really music. DeepBach is so skilled at replicating Bach that more than half of those surveyed had attributed its computer-generated melodies to the man himself — despite music students and professionals making up 25 percent of respondents. Critics generally deride tunes made by artificial intelligence by claiming these systems aren’t capable of generating art through creativity – be it text, music, or imagery. Enter MuseNet: a machine-learning algorithm developed by OpenAI that creates weird-and-wonderful music by predicting which sounds should follow user-inputted notes.…
This story continues at The Next Web
